@@ -173,6 +173,9 @@ struct fib6_info {
refcount_t fib6_ref;
unsigned long expires;
+
+ struct hlist_node gc_link;
+
struct dst_metrics *fib6_metrics;
#define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1]
@@ -241,12 +244,18 @@ static inline bool fib6_requires_src(const struct fib6_info *rt)
return rt->fib6_src.plen > 0;
}
+/* The callers should hold f6i->fib6_table->tb6_lock if a route has ever
+ * been added to a table before.
+ */
static inline void fib6_clean_expires(struct fib6_info *f6i)
{
f6i->fib6_flags &= ~RTF_EXPIRES;
f6i->expires = 0;
}
+/* The callers should hold f6i->fib6_table->tb6_lock if a route has ever
+ * been added to a table before.
+ */
static inline void fib6_set_expires(struct fib6_info *f6i,
unsigned long expires)
{
@@ -327,8 +336,10 @@ static inline bool fib6_info_hold_safe(struct fib6_info *f6i)
static inline void fib6_info_release(struct fib6_info *f6i)
{
- if (f6i && refcount_dec_and_test(&f6i->fib6_ref))
+ if (f6i && refcount_dec_and_test(&f6i->fib6_ref)) {
+ DEBUG_NET_WARN_ON_ONCE(!hlist_unhashed(&f6i->gc_link));
call_rcu(&f6i->rcu, fib6_info_destroy_rcu);
+ }
}
enum fib6_walk_state {
@@ -382,6 +393,7 @@ struct fib6_table {
struct inet_peer_base tb6_peers;
unsigned int flags;
unsigned int fib_seq;
+ struct hlist_head tb6_gc_hlist; /* GC candidates */
#define RT6_TABLE_HAS_DFLT_ROUTER BIT(0)
};
@@ -498,6 +510,27 @@ void fib6_gc_cleanup(void);
int fib6_init(void);
+/* Add the route to the gc list if it is not already there
+ *
+ * The callers should hold f6i->fib6_table->tb6_lock and make sure the
+ * route is on a table.
+ */
+static inline void fib6_add_gc_list(struct fib6_info *f6i)
+{
+ if (hlist_unhashed(&f6i->gc_link))
+ hlist_add_head(&f6i->gc_link, &f6i->fib6_table->tb6_gc_hlist);
+}
+
+/* Remove the route from the gc list if it is on the list.
+ *
+ * The callers should hold f6i->fib6_table->tb6_lock.
+ */
+static inline void fib6_remove_gc_list(struct fib6_info *f6i)
+{
+ if (!hlist_unhashed(&f6i->gc_link))
+ hlist_del_init(&f6i->gc_link);
+}
+
struct ipv6_route_iter {
struct seq_net_private p;
struct fib6_walker w;
@@ -1255,6 +1255,7 @@ static void
cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires,
bool del_rt, bool del_peer)
{
+ struct fib6_table *table;
struct fib6_info *f6i;
f6i = addrconf_get_prefix_route(del_peer ? &ifp->peer_addr : &ifp->addr,
@@ -1264,8 +1265,18 @@ cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires,
if (del_rt)
ip6_del_rt(dev_net(ifp->idev->dev), f6i, false);
else {
- if (!(f6i->fib6_flags & RTF_EXPIRES))
+ if (!(f6i->fib6_flags & RTF_EXPIRES)) {
+ table = f6i->fib6_table;
+ spin_lock_bh(&table->tb6_lock);
fib6_set_expires(f6i, expires);
+ /* If fib6_node is null, the f6i is just
+ * removed from the table.
+ */
+ if (rcu_dereference_protected(f6i->fib6_node,
+ lockdep_is_held(&table->tb6_lock)))
+ fib6_add_gc_list(f6i);
+ spin_unlock_bh(&table->tb6_lock);
+ }
fib6_info_release(f6i);
}
}
@@ -2706,6 +2717,7 @@ EXPORT_SYMBOL_GPL(addrconf_prefix_rcv_add_addr);
void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
{
struct prefix_info *pinfo;
+ struct fib6_table *table;
__u32 valid_lft;
__u32 prefered_lft;
int addr_type, err;
@@ -2782,11 +2794,23 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
if (valid_lft == 0) {
ip6_del_rt(net, rt, false);
rt = NULL;
- } else if (addrconf_finite_timeout(rt_expires)) {
- /* not infinity */
- fib6_set_expires(rt, jiffies + rt_expires);
} else {
- fib6_clean_expires(rt);
+ table = rt->fib6_table;
+ spin_lock_bh(&table->tb6_lock);
+ if (addrconf_finite_timeout(rt_expires)) {
+ /* not infinity */
+ fib6_set_expires(rt, jiffies + rt_expires);
+ /* If fib6_node is null, the f6i is
+ * just removed from the table.
+ */
+ if (rcu_dereference_protected(rt->fib6_node,
+ lockdep_is_held(&table->tb6_lock)))
+ fib6_add_gc_list(rt);
+ } else {
+ fib6_clean_expires(rt);
+ fib6_remove_gc_list(rt);
+ }
+ spin_unlock_bh(&table->tb6_lock);
}
} else if (valid_lft) {
clock_t expires = 0;
@@ -4741,6 +4765,7 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp,
unsigned long expires, u32 flags,
bool modify_peer)
{
+ struct fib6_table *table;
struct fib6_info *f6i;
u32 prio;
@@ -4761,10 +4786,21 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp,
ifp->rt_priority, ifp->idev->dev,
expires, flags, GFP_KERNEL);
} else {
- if (!expires)
+ table = f6i->fib6_table;
+ spin_lock_bh(&table->tb6_lock);
+ if (!expires) {
fib6_clean_expires(f6i);
- else
+ fib6_remove_gc_list(f6i);
+ } else {
fib6_set_expires(f6i, expires);
+ /* If fib6_node is null, the f6i is just removed
+ * from the table.
+ */
+ if (rcu_dereference_protected(f6i->fib6_node,
+ lockdep_is_held(&table->tb6_lock)))
+ fib6_add_gc_list(f6i);
+ }
+ spin_unlock_bh(&table->tb6_lock);
fib6_info_release(f6i);
}
@@ -160,6 +160,8 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh)
INIT_LIST_HEAD(&f6i->fib6_siblings);
refcount_set(&f6i->fib6_ref, 1);
+ INIT_HLIST_NODE(&f6i->gc_link);
+
return f6i;
}
@@ -246,6 +248,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
net->ipv6.fib6_null_entry);
table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
inet_peer_base_init(&table->tb6_peers);
+ INIT_HLIST_HEAD(&table->tb6_gc_hlist);
}
return table;
@@ -1055,6 +1058,9 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
lockdep_is_held(&table->tb6_lock));
}
}
+
+ fib6_clean_expires(rt);
+ fib6_remove_gc_list(rt);
}
/*
@@ -1115,10 +1121,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
rt->fib6_nsiblings = 0;
if (!(iter->fib6_flags & RTF_EXPIRES))
return -EEXIST;
- if (!(rt->fib6_flags & RTF_EXPIRES))
+ if (!(rt->fib6_flags & RTF_EXPIRES)) {
fib6_clean_expires(iter);
- else
+ fib6_remove_gc_list(iter);
+ } else {
fib6_set_expires(iter, rt->expires);
+ fib6_add_gc_list(iter);
+ }
if (rt->fib6_pmtu)
fib6_metric_set(iter, RTAX_MTU,
@@ -1477,6 +1486,10 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
if (rt->nh)
list_add(&rt->nh_list, &rt->nh->f6i_list);
__fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net));
+
+ if (rt->fib6_flags & RTF_EXPIRES)
+ fib6_add_gc_list(rt);
+
fib6_start_gc(info->nl_net, rt);
}
@@ -2280,9 +2293,8 @@ static void fib6_flush_trees(struct net *net)
* Garbage collection
*/
-static int fib6_age(struct fib6_info *rt, void *arg)
+static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args)
{
- struct fib6_gc_args *gc_args = arg;
unsigned long now = jiffies;
/*
@@ -2307,6 +2319,40 @@ static int fib6_age(struct fib6_info *rt, void *arg)
return 0;
}
+static void fib6_gc_table(struct net *net,
+ struct fib6_table *tb6,
+ struct fib6_gc_args *gc_args)
+{
+ struct fib6_info *rt;
+ struct hlist_node *n;
+ struct nl_info info = {
+ .nl_net = net,
+ .skip_notify = false,
+ };
+
+ hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link)
+ if (fib6_age(rt, gc_args) == -1)
+ fib6_del(rt, &info);
+}
+
+static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args)
+{
+ struct fib6_table *table;
+ struct hlist_head *head;
+ unsigned int h;
+
+ rcu_read_lock();
+ for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
+ head = &net->ipv6.fib_table_hash[h];
+ hlist_for_each_entry_rcu(table, head, tb6_hlist) {
+ spin_lock_bh(&table->tb6_lock);
+ fib6_gc_table(net, table, gc_args);
+ spin_unlock_bh(&table->tb6_lock);
+ }
+ }
+ rcu_read_unlock();
+}
+
void fib6_run_gc(unsigned long expires, struct net *net, bool force)
{
struct fib6_gc_args gc_args;
@@ -2322,7 +2368,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force)
net->ipv6.sysctl.ip6_rt_gc_interval;
gc_args.more = 0;
- fib6_clean_all(net, fib6_age, &gc_args);
+ fib6_gc_all(net, &gc_args);
now = jiffies;
net->ipv6.ip6_rt_last_gc = now;
@@ -2382,6 +2428,7 @@ static int __net_init fib6_net_init(struct net *net)
net->ipv6.fib6_main_tbl->tb6_root.fn_flags =
RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers);
+ INIT_HLIST_HEAD(&net->ipv6.fib6_main_tbl->tb6_gc_hlist);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl),
@@ -2394,6 +2441,7 @@ static int __net_init fib6_net_init(struct net *net)
net->ipv6.fib6_local_tbl->tb6_root.fn_flags =
RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers);
+ INIT_HLIST_HEAD(&net->ipv6.fib6_local_tbl->tb6_gc_hlist);
#endif
fib6_tables_init(net);
@@ -1410,8 +1410,17 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb)
inet6_rt_notify(RTM_NEWROUTE, rt, &nlinfo, NLM_F_REPLACE);
}
- if (rt)
+ if (rt) {
+ spin_lock_bh(&rt->fib6_table->tb6_lock);
fib6_set_expires(rt, jiffies + (HZ * lifetime));
+ /* If fib6_node is null, the f6i is just removed from the
+ * table.
+ */
+ if (rcu_dereference_protected(rt->fib6_node,
+ lockdep_is_held(&rt->fib6_table->tb6_lock)))
+ fib6_add_gc_list(rt);
+ spin_unlock_bh(&rt->fib6_table->tb6_lock);
+ }
if (in6_dev->cnf.accept_ra_min_hop_limit < 256 &&
ra_msg->icmph.icmp6_hop_limit) {
if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) {
@@ -989,10 +989,20 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
(rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
if (rt) {
- if (!addrconf_finite_timeout(lifetime))
+ spin_lock_bh(&rt->fib6_table->tb6_lock);
+ if (!addrconf_finite_timeout(lifetime)) {
fib6_clean_expires(rt);
- else
+ fib6_remove_gc_list(rt);
+ } else {
fib6_set_expires(rt, jiffies + HZ * lifetime);
+ /* If fib6_node is null, the f6i is just removed
+ * from the table.
+ */
+ if (rcu_dereference_protected(rt->fib6_node,
+ lockdep_is_held(&rt->fib6_table->tb6_lock)))
+ fib6_add_gc_list(rt);
+ }
+ spin_unlock_bh(&rt->fib6_table->tb6_lock);
fib6_info_release(rt);
}